FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200637211> ?p ?o ?g. }

• W3200637211 abstract "Deep learning techniques, such as deep neural networks (DNNs), have been used with success in many viral classification problems associated with metagenomics, diagnosis of viral infections, pharmacogenomics, phylogenetic analysis, and others. However, deep learning algorithms require a large number of math operations, and these computations themselves can be a bottleneck for processing the vast number of virus sequences in a short time. Currently, most works in this area use basic DNNs in viral classification, and they are not optimized for computational efficiency. This paper proposes a novel training strategy that simultaneously minimizes both pruning and quantization losses in training compressed models for reducing deep learning computational complexity. In training a compressed convolutional neural network (CNN), the scheme uses weight quantization followed by pruning in each training iteration rather than the pruning followed by quantization. The proposed training strategy scheme has been applied to train compressed models for efficient viral classification of 1600 sequences of four types of viruses associated with three families and one realm. A substantial reduction of DNN weights (77%) and operations (58%) is demonstrated, while maintaining high classification accuracy. These results show that the proposed new training regime of weight quantization followed weight pruning for each training iteration is superior to conventional approaches with weight pruning epochs followed by weight quantization epochs." @default.
• W3200637211 created "2021-09-27" @default.
• W3200637211 creator A5048556407 @default.
• W3200637211 creator A5066867900 @default.
• W3200637211 date "2021-07-18" @default.
• W3200637211 modified "2023-09-26" @default.
• W3200637211 title "A Novel Training Strategy for Deep Learning Model Compression Applied to Viral Classifications" @default.
• W3200637211 cites W2104267362 @default.
• W3200637211 cites W2171963266 @default.
• W3200637211 cites W2600768097 @default.
• W3200637211 cites W2776940252 @default.
• W3200637211 cites W2884491628 @default.
• W3200637211 cites W2903711666 @default.
• W3200637211 cites W2911892981 @default.
• W3200637211 cites W2915560701 @default.
• W3200637211 cites W2932459076 @default.
• W3200637211 cites W2949759087 @default.
• W3200637211 cites W2949831026 @default.
• W3200637211 cites W2950237782 @default.
• W3200637211 cites W2963140066 @default.
• W3200637211 cites W2963480671 @default.
• W3200637211 cites W2964299589 @default.
• W3200637211 cites W2966164316 @default.
• W3200637211 cites W2970102825 @default.
• W3200637211 cites W2973098646 @default.
• W3200637211 cites W2982479999 @default.
• W3200637211 cites W3001171417 @default.
• W3200637211 cites W3003110834 @default.
• W3200637211 cites W3003934875 @default.
• W3200637211 cites W3008594856 @default.
• W3200637211 cites W3011127849 @default.
• W3200637211 cites W3011188307 @default.
• W3200637211 cites W3013152614 @default.
• W3200637211 cites W3017384461 @default.
• W3200637211 cites W3017711809 @default.
• W3200637211 cites W3019119825 @default.
• W3200637211 cites W3021073680 @default.
• W3200637211 cites W3023132619 @default.
• W3200637211 cites W3027189436 @default.
• W3200637211 cites W3035085390 @default.
• W3200637211 cites W3038041907 @default.
• W3200637211 cites W3041044626 @default.
• W3200637211 cites W3091609397 @default.
• W3200637211 cites W3101091922 @default.
• W3200637211 cites W3130800274 @default.
• W3200637211 doi "https://doi.org/10.1109/ijcnn52387.2021.9534430" @default.
• W3200637211 hasPublicationYear "2021" @default.
• W3200637211 type Work @default.
• W3200637211 sameAs 3200637211 @default.
• W3200637211 citedByCount "0" @default.
• W3200637211 crossrefType "proceedings-article" @default.
• W3200637211 hasAuthorship W3200637211A5048556407 @default.
• W3200637211 hasAuthorship W3200637211A5066867900 @default.
• W3200637211 hasConcept C108010975 @default.
• W3200637211 hasConcept C108583219 @default.
• W3200637211 hasConcept C11413529 @default.
• W3200637211 hasConcept C119857082 @default.
• W3200637211 hasConcept C149635348 @default.
• W3200637211 hasConcept C153180895 @default.
• W3200637211 hasConcept C154945302 @default.
• W3200637211 hasConcept C2780513914 @default.
• W3200637211 hasConcept C28855332 @default.
• W3200637211 hasConcept C40567965 @default.
• W3200637211 hasConcept C41008148 @default.
• W3200637211 hasConcept C45374587 @default.
• W3200637211 hasConcept C50644808 @default.
• W3200637211 hasConcept C6557445 @default.
• W3200637211 hasConcept C81363708 @default.
• W3200637211 hasConcept C86803240 @default.
• W3200637211 hasConceptScore W3200637211C108010975 @default.
• W3200637211 hasConceptScore W3200637211C108583219 @default.
• W3200637211 hasConceptScore W3200637211C11413529 @default.
• W3200637211 hasConceptScore W3200637211C119857082 @default.
• W3200637211 hasConceptScore W3200637211C149635348 @default.
• W3200637211 hasConceptScore W3200637211C153180895 @default.
• W3200637211 hasConceptScore W3200637211C154945302 @default.
• W3200637211 hasConceptScore W3200637211C2780513914 @default.
• W3200637211 hasConceptScore W3200637211C28855332 @default.
• W3200637211 hasConceptScore W3200637211C40567965 @default.
• W3200637211 hasConceptScore W3200637211C41008148 @default.
• W3200637211 hasConceptScore W3200637211C45374587 @default.
• W3200637211 hasConceptScore W3200637211C50644808 @default.
• W3200637211 hasConceptScore W3200637211C6557445 @default.
• W3200637211 hasConceptScore W3200637211C81363708 @default.
• W3200637211 hasConceptScore W3200637211C86803240 @default.
• W3200637211 hasLocation W32006372111 @default.
• W3200637211 hasOpenAccess W3200637211 @default.
• W3200637211 hasPrimaryLocation W32006372111 @default.
• W3200637211 hasRelatedWork W2337926734 @default.
• W3200637211 hasRelatedWork W2732542196 @default.
• W3200637211 hasRelatedWork W2738221750 @default.
• W3200637211 hasRelatedWork W3156786002 @default.
• W3200637211 hasRelatedWork W3158053885 @default.
• W3200637211 hasRelatedWork W4311257506 @default.
• W3200637211 hasRelatedWork W4312417841 @default.
• W3200637211 hasRelatedWork W4320802194 @default.
• W3200637211 hasRelatedWork W4366224123 @default.
• W3200637211 hasRelatedWork W564581980 @default.
• W3200637211 isParatext "false" @default.
• W3200637211 isRetracted "false" @default.

• next